Imagen de Portada

Reinforcing 3D Understanding in Point-VLMs via Geometric Reward Credit Assignment

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chen, Jingkun, Xu, Ruoshi, Gao, Mingqi, Luo, Shengda, Han, Jungong
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Point Linguist Model: Segment Any Object via Bridged Large 3D-Language Model
por: Huang, Zhuoxu, et al.
Publicado: (2025)

Re-Prompting SAM 3 via Object Retrieval: 3rd of the 5th PVUW MOSE Track
por: Gao, Mingqi, et al.
Publicado: (2026)

The 1st Solution for MOSEv2 Challenge 2025: Long-term and Concept-aware Video Segmentation via SeC
por: Gao, Mingqi, et al.
Publicado: (2025)

SAM-Body4D: Training-Free 4D Human Body Mesh Recovery from Videos
por: Gao, Mingqi, et al.
Publicado: (2025)

1st Place Solution for MeViS Track in CVPR 2024 PVUW Workshop: Motion Expression guided Video Segmentation
por: Gao, Mingqi, et al.
Publicado: (2024)

THU-Warwick Submission for EPIC-KITCHEN Challenge 2025: Semi-Supervised Video Object Segmentation
por: Gao, Mingqi, et al.
Publicado: (2025)

MVPainter: Accurate and Detailed 3D Texture Generation via Multi-View Diffusion with Geometric Control
por: Shao, Mingqi, et al.
Publicado: (2025)

Show Me When and Where: Towards Referring Video Object Segmentation in the Wild
por: Gao, Mingqi, et al.
Publicado: (2026)

Unlocking the Potential of Diffusion Priors in Blind Face Restoration
por: Miao, Yunqi, et al.
Publicado: (2025)

On Exploring PDE Modeling for Point Cloud Video Representation Learning
por: Huang, Zhuoxu, et al.
Publicado: (2024)

SketchVL: Policy Optimization via Fine-Grained Credit Assignment for Chart Understanding and More
por: Huang, Muye, et al.
Publicado: (2026)

Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs
por: Li, Haoyuan, et al.
Publicado: (2025)

Part-Whole Relational Fusion Towards Multi-Modal Scene Understanding
por: Liu, Yi, et al.
Publicado: (2024)

WorldGenBench: A World-Knowledge-Integrated Benchmark for Reasoning-Driven Text-to-Image Generation
por: Zhang, Daoan, et al.
Publicado: (2025)

MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the Metaverse
por: Pan, Zhenyu, et al.
Publicado: (2025)

Leveraging Geometric Priors for Unaligned Scene Change Detection
por: Liu, Ziling, et al.
Publicado: (2025)

Rethinking Score Distilling Sampling for 3D Editing and Generation
por: Miao, Xingyu, et al.
Publicado: (2025)

Paving the Way for Point Cloud Video Representation Learning Using A PDE Model
por: Huang, Zhuoxu, et al.
Publicado: (2026)

Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understanding
por: Mei, Guofeng, et al.
Publicado: (2023)

UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding
por: Xu, Yueming, et al.
Publicado: (2025)

SimMLM: A Simple Framework for Multi-modal Learning with Missing Modality
por: Li, Sijie, et al.
Publicado: (2025)

3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding
por: Huang, Ting, et al.
Publicado: (2025)

GS-PT: Exploiting 3D Gaussian Splatting for Comprehensive Point Cloud Understanding via Self-supervised Learning
por: Liu, Keyi, et al.
Publicado: (2024)

Virtual Category Learning: A Semi-Supervised Learning Method for Dense Prediction with Extremely Limited Labels
por: Chen, Changrui, et al.
Publicado: (2023)

Guidance Contrastive Token Credit Assignment for Discrete Policy Optimization
por: Li, Shufan, et al.
Publicado: (2026)

SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs
por: Xu, Shuhan, et al.
Publicado: (2025)

POMA-3D: The Point Map Way to 3D Scene Understanding
por: Mao, Ye, et al.
Publicado: (2025)

RATopo: Improving Lane Topology Reasoning via Redundancy Assignment
por: Li, Han, et al.
Publicado: (2025)

VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement Learning
por: Zhang, Xuanyu, et al.
Publicado: (2025)

Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency
por: Li, Hongyu, et al.
Publicado: (2025)

PointRecon: Online Point-based 3D Reconstruction via Ray-based 2D-3D Matching
por: Ziwen, Chen, et al.
Publicado: (2024)

Spatial Preference Rewarding for MLLMs Spatial Understanding
por: Qiu, Han, et al.
Publicado: (2025)

ArtiWorld: LLM-Driven Articulation of 3D Objects in Scenes
por: Yang, Yixuan, et al.
Publicado: (2025)

Understanding Reward Hacking in Text-to-Image Reinforcement Learning
por: Hong, Yunqi, et al.
Publicado: (2026)

MolmoPoint: Better Pointing for VLMs with Grounding Tokens
por: Clark, Christopher, et al.
Publicado: (2026)

From Gaze to Insight: Bridging Human Visual Attention and Vision Language Model Explanation for Weakly-Supervised Medical Image Segmentation
por: Chen, Jingkun, et al.
Publicado: (2025)

LLaVA$^3$: Representing 3D Scenes like a Cubist Painter to Boost 3D Scene Understanding of VLMs
por: Petit, Doriand, et al.
Publicado: (2025)

More Text, Less Point: Towards 3D Data-Efficient Point-Language Understanding
por: Tang, Yuan, et al.
Publicado: (2024)

WaveFace: Authentic Face Restoration with Efficient Frequency Recovery
por: Miao, Yunqi, et al.
Publicado: (2024)

Exposing Vulnerabilities in Visible-Infrared VLMs: A Unified Geometric Adversarial Framework with Cross-Task Transferability
por: Chen, Xiang, et al.
Publicado: (2026)